@acedatacloud/skills 2026.807.0 → 2026.807.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@acedatacloud/skills",
3
- "version": "2026.807.0",
3
+ "version": "2026.807.1",
4
4
  "description": "Agent Skills for AceDataCloud AI services — music, image, video generation, LLM chat, web search. Compatible with Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and 30+ AI coding agents.",
5
5
  "keywords": [
6
6
  "agent-skills",
@@ -19,21 +19,23 @@ Generate 4–15 second videos through `POST https://api.acedata.cloud/minimax/vi
19
19
  | Parameter | Values | Default |
20
20
  | --- | --- | --- |
21
21
  | `model` | `minimax-h3` | `minimax-h3` |
22
- | `prompt` | non-empty string | conditional |
22
+ | `prompt` | non-empty string, max 7000 chars | required |
23
23
  | `image_urls` | 1–9 public HTTP(S) URLs | omitted |
24
24
  | `audio_urls` | 1–3 public HTTP(S) URLs | omitted |
25
+ | `resolution` | `768P`, `2K` | `2K` |
25
26
  | `ratio` | `16:9`, `9:16` | `16:9` |
27
+ | `aigc_watermark` | boolean | false |
26
28
  | `duration` | integer 4–15 | 4 |
27
29
  | `async` | boolean | false |
28
30
  | `callback_url` | public HTTP(S) webhook | omitted |
29
31
 
30
- At least one of `prompt`, `image_urls`, or `audio_urls` is required. Mode inference is deterministic:
32
+ `prompt` is required in every mode. Audio also requires at least one image. Mode inference is deterministic:
31
33
 
32
34
  1. `audio_urls` present → audio-guided video
33
35
  2. otherwise `image_urls` present → image-to-video
34
36
  3. otherwise → text-to-video
35
37
 
36
- Public price is **$0.25 per generated second**. Failed tasks are not charged.
38
+ Public pricing is **$0.057143/s for 768P** and **$0.091429/s for 2K** on the largest package. Failed tasks are not charged.
37
39
 
38
40
  ## Text to video
39
41
 
@@ -44,8 +46,9 @@ curl -X POST https://api.acedata.cloud/minimax/videos \
44
46
  -d '{
45
47
  "model": "minimax-h3",
46
48
  "prompt": "A red fox running through a snowy forest at dawn, low tracking shot",
49
+ "resolution": "768P",
47
50
  "ratio": "16:9",
48
- "duration": 6,
51
+ "duration": 4,
49
52
  "async": true
50
53
  }'
51
54
  ```
@@ -60,6 +63,7 @@ curl -X POST https://api.acedata.cloud/minimax/videos \
60
63
  "https://cdn.acedata.cloud/b1c82e4937.png",
61
64
  "https://cdn.acedata.cloud/eb75d88a3f.png"
62
65
  ],
66
+ "resolution": "768P",
63
67
  "ratio": "9:16",
64
68
  "duration": 8,
65
69
  "async": true
@@ -74,6 +78,7 @@ curl -X POST https://api.acedata.cloud/minimax/videos \
74
78
  "prompt": "A dancer moves naturally to the rhythm",
75
79
  "image_urls": ["https://cdn.acedata.cloud/b1c82e4937.png"],
76
80
  "audio_urls": ["https://cdn.acedata.cloud/6f7d62b18b.wav"],
81
+ "resolution": "768P",
77
82
  "ratio": "9:16",
78
83
  "duration": 8,
79
84
  "async": true
@@ -95,6 +100,7 @@ Continue polling about every five seconds until `response.success` is true or an
95
100
 
96
101
  - Do not send `action` to `/minimax/videos`; the API infers the mode from media inputs.
97
102
  - `duration` must be an integer, not a decimal.
98
- - Audio mode takes precedence when both image and audio arrays are present.
103
+ - Audio mode requires both `prompt` and at least one `image_urls` entry.
104
+ - Single-image mode uses the image as the first frame; multiple images are references.
99
105
  - Use public URLs that the generation service can download.
100
106
  - Returned videos are served from AceDataCloud CDN.